Oneirogen 1.5B by gustavecortal

 ยป  All LLMs  ยป  gustavecortal  ยป  Oneirogen 1.5B   URL Share it on

  Merged Model   Autotrain compatible   Conversational Dataset:gustavecortal/dreamban...   En   Endpoints compatible   Qwen2   Region:us   Safetensors

Oneirogen 1.5B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Oneirogen 1.5B (gustavecortal/oneirogen-1.5B)

Oneirogen 1.5B Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research
Applications:
dream generation, dream analysis
Primary Use Cases:
generate novel dream narratives
Additional Notes 
The model was inspired by Philip K. Dick's speech 'The Android and The Human' and can be fine-tuned on specific annotations for extended capabilities.
Supported Languages 
en (proficient)
Training Details 
Data Sources:
DreamBank
Data Volume:
27,000 dream narratives
Methodology:
LoRA adaptation
Model Architecture:
Qwen2
LLM NameOneirogen 1.5B
Repository ๐Ÿค—https://huggingface.co/gustavecortal/oneirogen-1.5B 
Merged ModelYes
Model Size1.5b
Required VRAM3.1 GB
Updated2025-01-20
Maintainergustavecortal
Model Typeqwen2
Model Files  3.1 GB
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.41.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Oneirogen 1.5B

Best Alternatives
Context / RAM
Downloads
Likes
ReaderLM V2500K / 3.5 GB2640275
Reader Lm 1.5B250K / 3.1 GB20065573
Qwen2.5 1.5B128K / 3.1 GB6701355
Stella En 1.5B V5128K / 6.2 GB594588206
NxMobileLM 1.5B SFT128K / 3.1 GB232
Qwen2 1.5B128K / 3.1 GB2859483
Gte Qwen2 1.5B Instruct128K / 7.1 GB176329155
SJT 1.5B Alpha 1.1128K / 3.6 GB90
Saba1 1.8B128K / 3.6 GB2500
Alpaca Data Ifd Min 2600128K / 3.1 GB150
Note: green Score (e.g. "73.2") means that the model is better than gustavecortal/oneirogen-1.5B.

Rank the Oneirogen 1.5B Capabilities

๐Ÿ†˜ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 41636 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227